Skill UI

Executes Pi in a non-interactive sessionless mode, parses its JSON event stream, and handles authentication and tool permissions. Useful for delegating bounded analysis or implementation tasks to Pi.

This skill compiles durable, non-obvious findings into an interlinked markdown knowledge store using atomic files and wiki links. It ensures agents retain knowledge across sessions without relearning facts. It involves creating one fact per file with metadata like confidence and provenance, maintaining an index for easy retrieval. Ideal for research, competitive intel, or investigation results.

This agent ensures perfect continuity between AI coding sessions by automatically saving session summaries, decisions, and pending tasks to local storage. It loads a detailed briefing at the start of new sessions, integrating with tools like Claude Code and Cursor to maintain project context without manual intervention.

This skill covers strategies for compressing conversation history in AI agent sessions to manage context window limits. It focuses on optimizing tokens-per-task rather than just tokens-per-request. Techniques include anchored iterative summarization, opaque compression, and regenerative summaries. It also addresses artifact trail integrity and evaluation methods like probe-based testing to ensure critical information like file paths and decisions are preserved during compression.

An intelligent context management specialist for capturing, serializing, and retrieving comprehensive project context across AI workflows. Supports semantic extraction, vector database integration, knowledge graphs, and multi-session collaboration.

This skill covers persistent memory systems for Large Language Model (LLM) conversations. It includes implementing short-term, long-term, and entity-based memory to enhance context retention across sessions. Features include memory consolidation, retrieval strategies, and integrating memory into prompts. Suitable for building conversational AI applications using tools like Mem0, LangChain, or Redis.

Ditto mines user words from local coding-agent session logs to create private work, design, and writing profiles. It requires explicit user approval before mining begins and keeps all data local. This skill routes a compatible Ditto runtime to extract patterns from real coding history rather than questionnaires, ensuring privacy and evidence-backed personalization for AI agents.

This skill outlines a discipline for capturing and redacting evidence in bug bounty submissions. It guides users on masking sensitive data like session cookies and PII while preserving triage-useful metadata. It covers protocols for screenshots, HAR files, and HTTP requests to prevent data leaks.

Maintain durable feature-level memory across AI coding sessions using lightweight Markdown tracks. It organizes status, source-of-truth docs, decisions, risks, and changes for long-lived features. Helps AI agents resume work accurately without relying on chat history. Ideal for repositories needing structured project memory without reorganizing all documentation.

Build real-time bidirectional streaming applications using the Gemini Live API. Supports WebSocket-based audio/video/text streaming, voice activity detection, function calling, and session management. Includes SDKs for Python and JavaScript for low-latency AI interactions.

Build background coding agents in remote sandboxed environments with image registries, warm pools, snapshots, and self-spawning sessions for scalable multiplayer execution.

This skill identifies session management vulnerabilities like session fixation, failure to invalidate sessions after logout or password changes, and weak session ID generation. It is designed for authorized security assessments to prevent Account Takeover (ATO) and unauthorized access. Users must obtain explicit written permission before testing targets.